INDEX

Explanations

occurrences of the phrase "of."

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

istrovstvÃŃ

-0.15

pot

-0.15

ego

-0.15

cken

-0.14

Ð³Ñĥ

-0.14

inya

-0.14

 Ð¾Ð´Ð¸

-0.14

hape

-0.13

á»ĩu

-0.13

ych

-0.13

POSITIVE LOGITS

 journal

0.18

 Journal

0.15

Î¯ÏĦ

0.15

 Bull

0.15

auc

0.15

Wire

0.14

wire

0.14

 journals

0.14

 Wire

0.14

_journal

0.14

Activations Density 0.031%

occurrences of the phrase "of."

No Comments

No Known Activations