INDEX

Explanations

narratives about character dynamics and moral ambiguity in storytelling

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

raph

-0.13

ãĥ©ãĤ¯

-0.13

 stere

-0.13

eum

-0.13

Accessor

-0.13

Ish

-0.12

opens

-0.12

 rever

-0.12

edor

-0.12

emoc

-0.12

POSITIVE LOGITS

MBED

0.15

UILDER

0.14

kening

0.14

 Citation

0.14

abd

0.14

oto

0.14

fuck

0.14

jay

0.13

_shader

0.13

zej

0.13

Activations Density 0.785%

narratives about character dynamics and moral ambiguity in storytelling

No Comments

No Known Activations