INDEX

Explanations

references to emotional and mental health, particularly in the context of community and recovery

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ivet

-0.18

irl

-0.16

itta

-0.15

ocab

-0.15

 sole

-0.14

vens

-0.14

istr

-0.14

ocal

-0.14

obic

-0.14

ukkit

-0.14

POSITIVE LOGITS

iaz

0.15

 Soph

0.15

uraa

0.15

uy

0.14

dee

0.14

egl

0.14

heimer

0.14

íľ´

0.14

 indirect

0.14

 goto

0.14

Activations Density 0.394%

references to emotional and mental health, particularly in the context of community and recovery

No Comments

No Known Activations