INDEX

Explanations

phrases and words related to family dynamics and personal appearance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

oba

-0.15

-hook

-0.14

hook

-0.14

ovo

-0.14

ear

-0.14

 bere

-0.13

rea

-0.13

 hook

-0.13

rame

-0.13

 Hook

-0.13

POSITIVE LOGITS

plode

0.16

ARING

0.15

ylon

0.15

.appspot

0.15

 libertin

0.14

blem

0.14

ForRow

0.14

ULA

0.14

_macros

0.14

Activations Density 0.250%

phrases and words related to family dynamics and personal appearance

No Comments

No Known Activations