INDEX

Explanations

instances of the word "first" and related actions indicating initial occurrences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ickey

-0.17

TS

-0.15

reeze

-0.15

stru

-0.15

oo

-0.14

 breed

-0.14

otor

-0.14

ambi

-0.14

 Reynolds

-0.14

hare

-0.14

POSITIVE LOGITS

YLE

0.15

infeld

0.15

Runner

0.15

eme

0.15

/msg

0.14

dux

0.14

Keeper

0.14

Ð½Ð°Ñĩ

0.14

urse

0.14

ãĥ¼ãĤ¹ãĥĪ

0.14

Activations Density 0.027%

instances of the word "first" and related actions indicating initial occurrences

No Comments

No Known Activations