INDEX

Explanations

specific nouns and dynamic verbs that indicate actions or processes related to structure and systems

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

 soft

-0.16

lesi

-0.16

te

-0.15

.orange

-0.15

Dol

-0.15

tic

-0.14

ene

-0.14

dap

-0.14

inese

-0.14

une

-0.14

POSITIVE LOGITS

adir

0.16

inton

0.15

ubat

0.14

asters

0.14

omu

0.14

aval

0.14

trx

0.14

imu

0.14

rish

0.13

 Initialized

0.13

Activations Density 0.019%

specific nouns and dynamic verbs that indicate actions or processes related to structure and systems

No Comments

No Known Activations