INDEX

Explanations

instances of intentional and deliberate actions or consequences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

/bit

-0.17

å¯Ħ

-0.15

rios

-0.15

alama

-0.15

ãģ¨ãĤĤ

-0.15

 Tham

-0.14

Sensitive

-0.14

lÃ¤

-0.14

ensitive

-0.14

 overall

-0.14

POSITIVE LOGITS

SED

0.19

ubar

0.17

fully

0.16

ously

0.16

gart

0.16

aidu

0.16

ably

0.15

atively

0.14

 intentional

0.14

iously

0.14

Activations Density 0.051%

instances of intentional and deliberate actions or consequences

No Comments

No Known Activations