INDEX

Explanations

key functional words and phrases that indicate connection, dependency, or relationships among concepts in technical or procedural contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

iciel

-0.17

aser

-0.16

åįĢ

-0.16

inski

-0.15

Î´Îµ

-0.15

DM

-0.14

äºĭ

-0.14

insk

-0.14

istrict

-0.14

/package

-0.14

POSITIVE LOGITS

ÙĪØ°

0.15

_hooks

0.14

preh

0.14

raman

0.14

ToLocal

0.14

INU

0.14

_mB

0.14

aker

0.14

Î¾Î¹

0.14

cas

0.14

Activations Density 0.002%

key functional words and phrases that indicate connection, dependency, or relationships among concepts in technical or procedural contexts

No Comments

No Known Activations