INDEX

Explanations

phrases that express transitions or transformations in states or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

 semiclass

-0.16

ashi

-0.15

 breath

-0.15

rael

-0.15

.Automation

-0.14

imore

-0.14

anton

-0.14

Äĥ

-0.14

ummer

-0.13

 denen

-0.13

POSITIVE LOGITS

/us

0.17

ÑĢÑĥÐ½

0.14

0.13

mue

0.13

/tos

0.13

arest

0.13

illis

0.13

-analytics

0.13

agers

0.13

ager

0.13

Activations Density 0.346%

phrases that express transitions or transformations in states or conditions

No Comments

No Known Activations