INDEX

Explanations

information about positions and roles related to job descriptions

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

ikip

-0.16

 Poetry

-0.15

 bleeding

-0.15

-e

-0.14

pass

-0.13

yy

-0.13

 poetry

-0.13

ickle

-0.13

POSITIVE LOGITS

ilon

0.17

onte

0.16

itesse

0.16

verbs

0.16

rians

0.15

 ------>

0.15

culo

0.15

 ifndef

0.15

ãĥ¼ãĤº

0.14

.handlers

0.14

Activations Density 0.312%

information about positions and roles related to job descriptions

No Comments

No Known Activations