INDEX

Explanations

overall assessments and summaries of experiences or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

.cgi

-0.16

ovich

-0.14

sono

-0.14

azines

-0.14

rk

-0.13

ADO

-0.13

swer

-0.13

xea

-0.13

affle

-0.13

#/

-0.13

POSITIVE LOGITS

icast

0.17

odian

0.17

pio

0.16

 overall

0.15

çĭĢ

0.15

ÙĩØ±Ùĩ

0.15

overall

0.15

*)((

0.14

é¬

0.14

CTL

0.14

Activations Density 0.021%

overall assessments and summaries of experiences or events

No Comments

No Known Activations