INDEX

Explanations

keywords or terms associated with locations, personal relationships, and specific contextual indicators

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

pace

-0.15

umont

-0.15

esson

-0.15

-0.14

erce

-0.14

 habit

-0.14

æĶ¾

-0.14

aida

-0.14

ainer

-0.13

claim

-0.13

POSITIVE LOGITS

iets

0.16

-cols

0.15

ãģŁãģĦ

0.15

ptest

0.14

odel

0.14

_constructor

0.14

apis

0.14

íĳľ

0.14

 cand

0.14

gesi

0.14

Activations Density 0.007%

keywords or terms associated with locations, personal relationships, and specific contextual indicators

No Comments

No Known Activations