INDEX

Explanations

mentions of news publications or media outlets

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

teri

-0.15

imir

-0.15

ido

-0.14

Ð°Ð´Ð¶

-0.14

works

-0.14

.jackson

-0.14

ossa

-0.14

ixa

-0.14

imit

-0.14

usk

-0.13

POSITIVE LOGITS

 inconsist

0.15

ÑĢÐ°Ð²Ð°

0.15

Ã¥n

0.14

riba

0.14

|.

0.14

 Died

0.14

_MULT

0.14

optimized

0.14

abee

0.13

uguay

0.13

Activations Density 0.036%

mentions of news publications or media outlets

No Comments

No Known Activations