INDEX

Explanations

technical terms and concepts related to software and coding frameworks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

æ¢ģ

-0.15

tan

-0.14

ibbon

-0.14

.idea

-0.14

aldi

-0.14

rna

-0.13

 Corrections

-0.13

_submission

-0.13

icle

-0.13

 Quantity

-0.13

POSITIVE LOGITS

ãĥ«ãĤ¯

0.16

balances

0.16

reet

0.15

ALES

0.15

jango

0.14

å¾Ħ

0.14

ectl

0.14

ieren

0.14

»

0.14

Monitor

0.14

Activations Density 0.001%

technical terms and concepts related to software and coding frameworks

No Comments

No Known Activations