INDEX

Explanations

important character names and their relationships in a narrative context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

Cl

-0.17

raph

-0.17

 composite

-0.15

Fen

-0.14

ene

-0.14

 Harbour

-0.14

Arc

-0.14

cl

-0.14

iral

-0.14

 substitute

-0.14

POSITIVE LOGITS

angan

0.20

 addCriterion

0.16

anian

0.15

sop

0.15

itore

0.15

trand

0.15

opak

0.15

ÎµÎ¹Î¿

0.15

ãĥ¼ãĥķ

0.15

Activations Density 0.094%

important character names and their relationships in a narrative context

No Comments

No Known Activations