INDEX

Explanations

mentions of television and related media platforms

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

AVOR

-0.14

tit

-0.14

.hs

-0.14

pard

-0.14

urch

-0.14

ezi

-0.13

VIS

-0.13

á¿¶

-0.13

ringe

-0.13

adm

-0.13

POSITIVE LOGITS

 Steele

0.16

ritz

0.15

lein

0.14

ForObject

0.14

 ration

0.14

 Pron

0.14

 Stern

0.14

.ht

0.14

 taps

0.14

ounces

0.14

Activations Density 0.007%

mentions of television and related media platforms

No Comments

No Known Activations