INDEX

Explanations

terms related to specific reviews, ratings, or mentions of products and services

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

oda

-0.15

 Habit

-0.15

-0.14

ocab

-0.14

 habit

-0.13

_CHUNK

-0.13

ese

-0.13

Compiled

-0.13

Å£i

-0.13

pez

-0.13

POSITIVE LOGITS

.com

0.18

atre

0.16

gether

0.16

aken

0.16

ÎµÏģÎ¹

0.15

verage

0.15

.blob

0.14

chest

0.14

ÙĦØ§Ùħ

0.14

atever

0.14

Activations Density 0.302%

terms related to specific reviews, ratings, or mentions of products and services

No Comments

No Known Activations