INDEX

Explanations

words associated with social interactions and connections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

-0.17

ÑģÑĤÐ²Ð¾ÑĢ

-0.15

ingly

-0.15

 Preferences

-0.14

Utility

-0.14

_endpoint

-0.14

jam

-0.13

upa

-0.13

jel

-0.13

andler

-0.13

POSITIVE LOGITS

nier

0.16

ansen

0.15

ucks

0.15

 tabindex

0.15

Ð°Ð»ÐµÐ¶

0.14

otime

0.14

seller

0.14

 Communic

0.14

hled

0.14

 ((__

0.14

Activations Density 0.002%

words associated with social interactions and connections

No Comments

No Known Activations