INDEX

Explanations

phrases related to descriptions and evaluations of objects or situations

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

elib

-0.16

iek

-0.15

ãģ£ãģ¨

-0.14

Ves

-0.13

çĶ

-0.13

aise

-0.13

isa

-0.13

 Ð¾Ñĩ

-0.13

edm

-0.13

POSITIVE LOGITS

rys

0.16

regnum

0.14

undan

0.13

ãĥ¼ãĥį

0.13

gan

0.13

peg

0.13

ÙĪÙĦÛĮ

0.13

Speak

0.13

.unsplash

0.13

Activations Density 1.286%

phrases related to descriptions and evaluations of objects or situations

No Comments

No Known Activations