INDEX

Explanations

concepts related to health and nutrition specifically focusing on ingredients and their effects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

incinn

-0.17

atak

-0.16

dete

-0.16

rint

-0.15

ãĥªãĥ¼ãĤº

-0.15

amate

-0.15

æĮ¯ãĤĬ

-0.14

quist

-0.14

raph

-0.14

ords

-0.14

POSITIVE LOGITS

 gang

0.16

AGMA

0.15

asser

0.15

avers

0.15

so

0.14

 Marr

0.14

-packed

0.14

unt

0.13

Ł

0.13

ETA

0.13

Activations Density 0.135%

concepts related to health and nutrition specifically focusing on ingredients and their effects

No Comments

No Known Activations