INDEX

Explanations

phrases that reference reading or written text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

ÙĦØ¨

-0.16

åĸ

-0.15

Î±ÏģÎ¬

-0.14

 struggles

-0.14

erap

-0.13

ct

-0.13

Ov

-0.13

abolic

-0.13

 Bread

-0.13

åĳ

-0.13

POSITIVE LOGITS

ì»¤ìĬ¤

0.17

çŃĳ

0.16

Chr

0.16

Ral

0.16

 Teach

0.16

needle

0.15

.ta

0.14

á»Ľ

0.14

æ¾¤

0.14

agem

0.14

Activations Density 0.046%

phrases that reference reading or written text

No Comments

No Known Activations