INDEX

Explanations

words related to entertainment or media content

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

-0.15

rong

-0.15

unken

-0.15

éĸ

-0.15

uien

-0.15

 carrier

-0.14

aneous

-0.14

onomy

-0.14

 carriers

-0.14

 Decomp

-0.14

POSITIVE LOGITS

Ler

0.15

aura

0.15

_fp

0.14

ç¤

0.14

fon

0.14

aviest

0.14

ston

0.14

Wie

0.14

ereum

0.13

BackPressed

0.13

Activations Density 0.001%

words related to entertainment or media content

No Comments

No Known Activations