INDEX

Explanations

references to comparisons or trends regarding quantity and similarity among subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

.mit

-0.16

stva

-0.16

inia

-0.16

ush

-0.15

ÑģÑĤÐ²Ñĥ

-0.15

;base

-0.14

 encaps

-0.14

igraph

-0.14

 (...)

-0.14

ulet

-0.14

POSITIVE LOGITS

zek

0.17

emale

0.14

utterstock

0.14

OfClass

0.14

itler

0.14

iare

0.14

blank

0.13

hone

0.13

 Toll

0.13

decess

0.13

Activations Density 0.046%

references to comparisons or trends regarding quantity and similarity among subjects

No Comments

No Known Activations