INDEX

Explanations

occurrences of specific symbols or characters, potentially indicating a focus on formatting or special content within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

uffman

-0.15

-lite

-0.14

 temps

-0.14

ÐºÐ¾Ð´

-0.13

 Binder

-0.13

uÃŃ

-0.13

FRING

-0.13

isl

-0.13

æĹıèĩªæ²»

-0.12

_EXTERN

-0.12

POSITIVE LOGITS

 Cinema

0.15

 narr

0.15

sor

0.14

 cinema

0.14

 Egyptians

0.14

merc

0.14

 neither

0.14

Sor

0.14

 homelessness

0.14

Activations Density 0.007%

occurrences of specific symbols or characters, potentially indicating a focus on formatting or special content within the text

No Comments

No Known Activations