INDEX

Explanations

words related to entertainment

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ÑĩÐ°ÑĤ

-0.16

assi

-0.16

 Savage

-0.15

Steel

-0.15

 Ritch

-0.14

Gra

-0.14

edo

-0.14

ãģĹãģı

-0.14

 Vanilla

-0.14

POSITIVE LOGITS

akash

0.15

ÑŁ

0.15

zione

0.14

apesh

0.14

 Injector

0.14

ELLOW

0.14

ffffffff

0.13

opic

0.13

shint

0.13

agner

0.13

Activations Density 0.000%

words related to entertainment

No Comments

No Known Activations