INDEX

Explanations

references to storytelling or narratives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

ovich

-0.17

ir

-0.14

teness

-0.14

(PR

-0.14

Ãłi

-0.14

rog

-0.14

ãĥ¥

-0.14

ÐµÐ²Ð¸Ñĩ

-0.13

rogate

-0.13

------+------+

-0.13

POSITIVE LOGITS

 story

0.56

 Story

0.48

 stories

0.46

story

0.45

Story

0.44

 tale

0.42

 STORY

0.40

_story

0.40

 Stories

0.40

-story

0.38

Activations Density 0.034%

references to storytelling or narratives

No Comments

No Known Activations