INDEX

Explanations

conjunctions and linking words that lead into explanations or elaborations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

jm

-0.16

isque

-0.15

eya

-0.15

ÑĽ

-0.15

yla

-0.15

nze

-0.14

ntag

-0.14

elu

-0.14

ç¹ģ

-0.14

avou

-0.14

POSITIVE LOGITS

 sÄ±

0.16

ãĤ¤ãĤ¹

0.15

 Nielsen

0.15

idl

0.14

 Andersen

0.14

 arranged

0.14

Ã¡Äį

0.14

extr

0.14

Ð¾Ð±ÑīÐµ

0.14

 pocket

0.13

Activations Density 0.204%

conjunctions and linking words that lead into explanations or elaborations

No Comments

No Known Activations