INDEX

Explanations

expressions of symbolism and representation related to memorials and tributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

-0.15

-0.14

isia

-0.14

caffold

-0.14

 reimb

-0.14

kontakte

-0.14

Ãªn

-0.14

 suspicious

-0.14

adena

-0.14

POSITIVE LOGITS

 testimony

0.36

 reminder

0.33

 testament

0.33

 symbol

0.32

 sign

0.31

 representation

0.30

 statement

0.30

 indicator

0.28

 proof

0.27

 testim

0.27

Activations Density 0.223%

expressions of symbolism and representation related to memorials and tributes

No Comments

No Known Activations