INDEX

Explanations

expressions of personal feelings and opinions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

 kinh

-0.16

Î¼Î±ÏĦÎ¿

-0.15

abic

-0.15

éĺµ

-0.14

å·»

-0.14

 considering

-0.14

 ÎļÎ¬

-0.14

Decre

-0.13

.criteria

-0.13

Ķ

-0.13

POSITIVE LOGITS

 crib

0.24

 sieve

0.16

 hood

0.16

 anyways

0.16

 visual

0.16

vala

0.15

IFA

0.15

pole

0.15

 intros

0.15

 anyway

0.15

Activations Density 0.261%

expressions of personal feelings and opinions

No Comments

No Known Activations