INDEX

Explanations

terms related to various philosophical and ideological positions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

er

-0.22

izer

-0.17

nier

-0.16

an

-0.15

æĿī

-0.15

smith

-0.15

umas

-0.15

åº¦

-0.15

anine

-0.15

thon

-0.15

POSITIVE LOGITS

(ic

0.22

ically

0.21

ische

0.21

-leaning

0.21

otle

0.20

isches

0.17

ycz

0.16

lero

0.16

Ð¸Ñĩ

0.16

ischer

0.15

Activations Density 0.084%

terms related to various philosophical and ideological positions

No Comments

No Known Activations