INDEX

Explanations

references to organizations, particularly related to film and media

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

iminal

-0.18

rani

-0.17

 Kaiser

-0.15

imei

-0.15

uala

-0.14

uco

-0.14

ÃŃst

-0.13

rego

-0.13

lico

-0.13

vsp

-0.13

POSITIVE LOGITS

amble

0.14

Ð½Ð³

0.14

 Strait

0.14

others

0.13

 Others

0.13

igner

0.13

ãĥ£

0.13

ValueChanged

0.13

Activations Density 0.519%

references to organizations, particularly related to film and media

No Comments

No Known Activations