INDEX

Explanations

contexts involving deletion or removal

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

naments

-0.14

gi

-0.14

 impro

-0.14

DN

-0.14

stanov

-0.13

Î»Î¹Î¬

-0.13

ly

-0.13

azzo

-0.13

sep

-0.13

worm

-0.13

POSITIVE LOGITS

pedia

0.18

ivor

0.16

zilla

0.16

iert

0.15

.mapping

0.15

 Coloring

0.15

itung

0.14

icits

0.14

ãĥ¬ãĥĥãĥĪ

0.14

Activations Density 0.027%

contexts involving deletion or removal

No Comments

No Known Activations