INDEX

Explanations

section headlines and markers in structured documents or code

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

ollo

-0.17

rani

-0.17

dep

-0.16

iegel

-0.16

rong

-0.16

enna

-0.15

ickers

-0.14

eking

-0.14

wel

-0.14

/upload

-0.14

POSITIVE LOGITS

ambi

0.14

ijkstra

0.14

UNDLE

0.14

RTOS

0.14

 Achilles

0.13

ODY

0.13

BIND

0.13

chod

0.13

 Truy

0.13

Activations Density 0.032%

section headlines and markers in structured documents or code

No Comments

No Known Activations