INDEX

Explanations

terms and concepts related to systems, organization, and readiness for processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

aba

-0.16

 earm

-0.15

eya

-0.15

rij

-0.15

 Partial

-0.14

iyan

-0.14

 partial

-0.14

 tons

-0.14

ieder

-0.14

 hind

-0.13

POSITIVE LOGITS

ifton

0.15

Ð¾ÑĢÐ¾Ð²

0.15

 Tatto

0.14

HT

0.14

 Cathedral

0.14

inge

0.14

uliar

0.14

ZF

0.14

nic

0.14

 ç¬

0.14

Activations Density 0.030%

terms and concepts related to systems, organization, and readiness for processes

No Comments

No Known Activations