INDEX

Explanations

occurrences of words or phrases that indicate social connections or relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

ÅĻit

-0.14

SPATH

-0.14

GLOSS

-0.13

bindValue

-0.13

MG

-0.13

 Forbes

-0.12

CLUS

-0.12

áº¹n

-0.12

ongsTo

-0.12

mpz

-0.12

POSITIVE LOGITS

 Fleming

0.44

 Bram

0.44

 Biom

0.44

Yam

0.43

 biom

0.43

LEM

0.40

 Grimm

0.39

Vim

0.39

PCM

0.39

 McMahon

0.39

Activations Density 0.355%

occurrences of words or phrases that indicate social connections or relationships

No Comments

No Known Activations