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

olley

-0.15

å¾

-0.14

ÚĨÛĮ

-0.14

ì´

-0.14

AMERA

-0.14

ÌĨ

-0.14

-Identifier

-0.14

TouchUpInside

-0.14

pon

-0.14

sembles

-0.14

POSITIVE LOGITS

 Mouse

0.14

pas

0.14

 disc

0.14

 Good

0.14

quo

0.14

 surv

0.14

imas

0.14

ever

0.14

ElementException

0.14

Activations Density 0.000%

words related to entertainment

No Comments

No Known Activations