INDEX

Explanations

occurrences of "Times" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ieri

-0.16

ts

-0.15

hin

-0.15

è¢ĭ

-0.15

 Pitch

-0.15

 tiener

-0.15

att

-0.15

asser

-0.15

arg

-0.15

wers

-0.14

POSITIVE LOGITS

.pt

0.17

UNET

0.15

osterone

0.15

 burn

0.14

lk

0.14

uzey

0.14

 getActivity

0.14

ESH

0.14

_PK

0.14

ories

0.13

Activations Density 0.009%

occurrences of "Times" in various contexts

No Comments

No Known Activations