INDEX

Explanations

references to formal assessments, evaluations, or financial metrics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

amb

-0.17

ibble

-0.16

 Merr

-0.16

-0.15

ten

-0.15

atif

-0.14

ugins

-0.14

 Jarvis

-0.14

zig

-0.14

Jam

-0.14

POSITIVE LOGITS

 Gould

0.16

 Lionel

0.15

ilon

0.15

sey

0.15

stvo

0.15

 pill

0.15

azon

0.14

 Braun

0.14

 Carson

0.14

cea

0.14

Activations Density 0.023%

references to formal assessments, evaluations, or financial metrics

No Comments

No Known Activations