INDEX

Explanations

phrases related to health, travel, and missing persons investigations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

 Damen

-0.16

Sco

-0.16

afen

-0.15

vet

-0.14

ç¢¼

-0.14

opian

-0.14

Ø§ÙĬØª

-0.14

mute

-0.14

Jew

-0.13

sit

-0.13

POSITIVE LOGITS

iko

0.16

raig

0.15

Ð°ÑĢÑĤÐ°Ð¼

0.15

sie

0.14

ipy

0.14

.Params

0.14

ittings

0.14

0.13

Sie

0.13

Activations Density 0.256%

phrases related to health, travel, and missing persons investigations

No Comments

No Known Activations