INDEX

Explanations

references to people and their actions or attributes

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

-0.18

 preference

-0.16

-0.15

stract

-0.15

ouble

-0.14

ÙĦÙģ

-0.14

Ben

-0.14

 encounter

-0.14

cran

-0.13

POSITIVE LOGITS

Ø§Ø¯Ùħ

0.15

eÄį

0.15

Ð±Ð¾

0.15

ØªØ§

0.15

hq

0.14

anton

0.14

_SA

0.14

innen

0.14

ater

0.14

ause

0.13

Activations Density 0.004%

references to people and their actions or attributes

No Comments

No Known Activations