INDEX

Explanations

parts of speech indicating actions or experiences, particularly focused on the past tense or participle forms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

/cgi

-0.17

á»Ĳ

-0.17

avenport

-0.15

.datatables

-0.15

ewire

-0.15

-0.14

á»±

-0.13

kker

-0.13

carousel

-0.13

eshire

-0.13

POSITIVE LOGITS

rg

0.14

aren

0.14

allest

0.14

ible

0.14

oret

0.14

yd

0.13

 organism

0.13

vit

0.13

munition

0.13

Activations Density 0.214%

parts of speech indicating actions or experiences, particularly focused on the past tense or participle forms

No Comments

No Known Activations