INDEX

Explanations

words related to entertainment or media

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

;amp

-0.15

 EÅŁ

-0.15

ÑĢÐ¸ÑĤÐ¸

-0.15

æĭĽ

-0.15

azzi

-0.15

gatsby

-0.14

OTH

-0.14

_flutter

-0.14

elines

-0.13

POSITIVE LOGITS

pend

0.17

áº¥p

0.16

ÅĤaw

0.15

 Kraj

0.15

 cáº¥p

0.15

ling

0.15

å¥Ĺ

0.15

llib

0.14

cast

0.14

-o

0.14

Activations Density 0.000%

words related to entertainment or media

No Comments

No Known Activations